question about the model.py

[Liz66666]

Hi @hackiey , Thanks for your code. But I still have a question about the network in your implement. Paper said that "we employ atrous convolution to generate the 3 · K predictions", but in your model.py, you used nn.ConvTranspose2d. Is these two methods same? https://github.com/hackiey/keypoints/blob/a676ef08ee8f32d68d2fa1273955cf3ff7b5f9f4/src/model.py#L24

[HowieMa]

In line 10: self.num_outputs = num_classes * 3